summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorOleg Nesterov <oleg@redhat.com>2016-11-14 19:46:09 +0100
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2017-10-27 10:23:17 +0200
commit0f85c0954be46bbd36960191daa447ad86b98f0b (patch)
treea3402ef06ed231bd868af3921906af7ffc4964db /kernel
parentfcc65ab173ebf797472b046f2d84663fbbe443a7 (diff)
sched/autogroup: Fix autogroup_move_group() to never skip sched_move_task()
commit 18f649ef344127ef6de23a5a4272dbe2fdb73dde upstream. The PF_EXITING check in task_wants_autogroup() is no longer needed. Remove it, but see the next patch. However the comment is correct in that autogroup_move_group() must always change task_group() for every thread so the sysctl_ check is very wrong; we can race with cgroups and even sys_setsid() is not safe because a task running with task_group() == ag->tg must participate in refcounting: int main(void) { int sctl = open("/proc/sys/kernel/sched_autogroup_enabled", O_WRONLY); assert(sctl > 0); if (fork()) { wait(NULL); // destroy the child's ag/tg pause(); } assert(pwrite(sctl, "1\n", 2, 0) == 2); assert(setsid() > 0); if (fork()) pause(); kill(getppid(), SIGKILL); sleep(1); // The child has gone, the grandchild runs with kref == 1 assert(pwrite(sctl, "0\n", 2, 0) == 2); assert(setsid() > 0); // runs with the freed ag/tg for (;;) sleep(1); return 0; } crashes the kernel. It doesn't really need sleep(1), it doesn't matter if autogroup_move_group() actually frees the task_group or this happens later. Reported-by: Vern Lovejoy <vlovejoy@redhat.com> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: hartsjc@redhat.com Cc: vbendel@redhat.com Link: http://lkml.kernel.org/r/20161114184609.GA15965@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org> [sumits: submit to 4.4 LTS, post testing on Hikey] Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/sched/auto_group.c23
1 files changed, 12 insertions, 11 deletions
diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c
index 750ed601ddf7..8620fd01b3d0 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/auto_group.c
@@ -111,14 +111,11 @@ bool task_wants_autogroup(struct task_struct *p, struct task_group *tg)
{
if (tg != &root_task_group)
return false;
-
/*
- * We can only assume the task group can't go away on us if
- * autogroup_move_group() can see us on ->thread_group list.
+ * If we race with autogroup_move_group() the caller can use the old
+ * value of signal->autogroup but in this case sched_move_task() will
+ * be called again before autogroup_kref_put().
*/
- if (p->flags & PF_EXITING)
- return false;
-
return true;
}
@@ -138,13 +135,17 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
}
p->signal->autogroup = autogroup_kref_get(ag);
-
- if (!READ_ONCE(sysctl_sched_autogroup_enabled))
- goto out;
-
+ /*
+ * We can't avoid sched_move_task() after we changed signal->autogroup,
+ * this process can already run with task_group() == prev->tg or we can
+ * race with cgroup code which can read autogroup = prev under rq->lock.
+ * In the latter case for_each_thread() can not miss a migrating thread,
+ * cpu_cgroup_attach() must not be possible after cgroup_exit() and it
+ * can't be removed from thread list, we hold ->siglock.
+ */
for_each_thread(p, t)
sched_move_task(t);
-out:
+
unlock_task_sighand(p, &flags);
autogroup_kref_put(prev);
}